From f9eda09deaa2247070ab472f4786f48a2eddb9c0 Mon Sep 17 00:00:00 2001
From: dusk <strangealt@protonmail.com>
Date: Wed, 21 Feb 2024 17:47:29 +0100
Subject: [PATCH] Use csv file for intermediary parsing

---
 src/orig.py   |  1 +
 src/parser.py | 76 ++++++++++++++++++++++++++++++++++-----------------
 2 files changed, 52 insertions(+), 25 deletions(-)

diff --git a/src/orig.py b/src/orig.py
index b46cf9d..1ddd67a 100755
--- a/src/orig.py
+++ b/src/orig.py
@@ -131,6 +131,7 @@ def get_symbols(line: str) -> (str, list[str]):
 def write_translated(outfile, origfile, translation_file_paths):
     for transfilepath in translation_file_paths:
         print(f'- reading "{transfilepath}"')
+        parser.parse_to_csv(transfilepath)
         structure = parser.parse_to_structure(transfilepath)
 
         for line in origfile:
diff --git a/src/parser.py b/src/parser.py
index 8f9afef..fb88804 100755
--- a/src/parser.py
+++ b/src/parser.py
@@ -1,15 +1,16 @@
 #!/usr/bin/env python3
 
+import csv
 import os
 import config
 
 class OutputLine():
-    def __init__(self, text_jp: str, text_en: str, type: str):
+    def __init__(self, text_jp: str, text_en: str):
         self.text_jp = text_jp
         self.text_en = text_en
-        self.type = type
+        # self.type = type
 
-def get_functions_from_file(filepath: str):
+def get_functions_from_file(filepath: str) -> list[str]:
     """
     Gets the function calls from a file and returns
     a list of lists with the following structure:
@@ -89,33 +90,58 @@ def get_functions_from_file(filepath: str):
 
     return tokens
 
+def parse_to_csv(filename: str):
+    out_path = config.get('output_path')
+    scripts_path = config.get('scripts_path')
 
-def parse_to_structure(filename: str):
-    scripts_path = config.get("scripts_path")
+    csvname = os.path.join(out_path, filename + ".csv")
+    escapechar = config.get('csv_escapechar')
+    delchar = config.get('csv_delchar')
 
-    tokens = get_functions_from_file(
-        os.path.join(scripts_path, filename)
-    )
+    with open(csvname, 'w') as csvfile:
 
-    structure = []
+        csv_writer = csv.writer(
+            csvfile,
+            delimiter=delchar,
+            quoting=csv.QUOTE_ALL,
+            quotechar=escapechar,
+        )
 
-    for token in tokens:
-        function_name = token[0]
+        tokens = get_functions_from_file(
+            os.path.join(scripts_path, filename)
+        )
 
-        if function_name == "OutputLine":
-            structure.append(OutputLine(
-                text_jp=token[2][1:-1].replace('\\', ''),
-                text_en=token[4][1:-1].replace('\\', ''),
-                type=token[-1],
-            ))
+        for token in tokens:
+            function_name = token[0]
 
-        elif (
-            function_name == "OutputLineAll"
-            and "Line_ContinueAfterTyping" == token[-1]
-            and "\\n" in token[2]
-        ):
-            pass
-            #count = token[2].count("\\n")
-            # structure.append(["LineBreak", count])
+            if function_name == "OutputLine":
+                #NOTE: [1:-1] Removes quotes
+                text_jp = token[2][1:-1].replace('\\', '').replace('\n', '')
+                text_en = token[4][1:-1].replace('\\', '').replace('\n', '')
+                csv_writer.writerow([text_jp, text_en])
+
+
+def parse_to_structure(filename: str) -> list[OutputLine]:
+    out_path = config.get('output_path')
+    csvname = os.path.join(out_path, filename + ".csv")
+    escapechar = config.get('csv_escapechar')
+    delchar = config.get('csv_delchar')
+
+    with open(csvname, 'r') as csvfile:
+        csv_reader = csv.reader(
+            csvfile,
+            delimiter=delchar,
+            quotechar=escapechar,
+        )
+
+        structure = []
+
+        for row in csv_reader:
+            structure.append(
+                OutputLine(
+                    text_jp=row[0],
+                    text_en=row[1]
+                )
+            )
 
     return structure